01efdd42-cc93-4498-8836-5416e798b1c6

This model is a fine-tuned version of NousResearch/GPT4-x-Vicuna-13b-fp16 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.2513

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.000208
• train_batch_size: 4
• eval_batch_size: 4
• seed: 80
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0008	1	2.9869
2.6371	0.0419	50	2.4640
2.5372	0.0839	100	2.5468
2.5542	0.1258	150	2.4662
2.5761	0.1677	200	2.4173
2.6806	0.2096	250	2.3430
2.5811	0.2516	300	2.3232
2.3769	0.2935	350	2.2691
2.5571	0.3354	400	2.2556
2.629	0.3774	450	2.2486
2.5459	0.4193	500	2.2513

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1